-
I can obtain episode reward mean from the train result, but the fluctuation is very large, and it is difficult to judge when to stop the training iteration, so I hope to use the result of evaluate.
…
-
May I ask why the author does not want to use pipe to load each module, such as unet, when reasoning during training
-
Hello,
I really appreciate your work and the extensive codebase!
I am trying to reproduce the results from the paper with the dataset from LMDrive.
For that, I fused both LiDAR folders and sampled …
-
Hi,
Just wondering if the trained models are available somewhere to access. If possible, could you please share it?
-
As I've mentioned in the title, I have some huge text based documents which exceed typical context windows, even on large machines with large models (e.g. 405B). Is there a way I could train llama 3.1…
-
I use this setting below to train flux lora:
```
accelerate launch --gpu_ids 0,1 --main_process_port 29502 --mixed_precision bf16 --num_cpu_threads_per_process=2 \
flux_train_network.py --pr…
-
### 问题确认 Search before asking
- [X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.
### 请提出你的问题 Please ask your question
![image](https://github.com/PaddlePaddle/Paddle…
-
I've installed 1.1.0 yet the Tender and Sluf are still marked as C-XXX instead of their new ID.
I'me made sure to set Prefixes on "Model Based"
-
I'm encountering an issue while training the Waveformer model. When I run the following command:
python -W ignore -m src.training.train /home/swufe1/project/Waveformer/experiments/dcc_tf_ckpt_E256…
-
**Is your feature request related to a problem? Please describe.**
Extremely modded playthroughs run into the issue of trains not being fast enough and forces me to build wider train tracks and put d…